Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98389
    Prev
    Next
    INDEX
    Explanations

    об

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provident
    -0.08
    .]↵
    -0.08
    .')↵
    -0.08
    Mort
    -0.08
     ugly
    -0.08
    .er
    -0.07
     Mort
    -0.07
    .")↵
    -0.07
    -0.07
    .`);↵
    -0.07
    POSITIVE LOGITS
    ेज
    0.10
    -arrow
    0.09
    -slide
    0.09
    ziwe
    0.09
    -ba
    0.08
    ze
    0.08
    ೇಜ
    0.08
    -check
    0.08
    -tour
    0.08
    ేజ
    0.08
    Activations Density 0.000%

    No Known Activations